Group Preference Modelling in SMAA using Belief Functions

R. Lahdelma (Finland), T. Tervonen (Finland, Portugal), P. Salminen (Finland), and J. Figueira (Portugal)

Keywords

Stochastic Multicriteria Acceptability Analysis, Preference Modelling, Multicriteria Decision Aiding, Group Decision Making

Abstract

Stochastic Multicriteria Acceptability Analysis (SMAA) is a family of methods to aid decision makers (DMs) in dis crete decision making problems. SMAA methods are ca pable of handling preference information of various types. The imperfect knowledge about the preferences of multiple DMs can for example be represented by a joint probability distribution for criteria weights (scale factors). Dempster-Shafer theory of evidence (DST) is a gen eralization of the classic Bayesian probability theory, that allows modelling of ignorance by using belief functions. In this paper we show how the preferences of multiple DMs can be modelled and combined using DST, and how this information can then be encoded as interval constraints for sets of weights in SMAA.

Important Links:



Go Back